Perplexity rolls out effort controls in Computer; user shares a 3-tier model workflow
inductionheads · x · 2026-09-18
Perplexity is rolling out effort controls in Computer's model selector: presets combine the orchestrator model with reasoning depth to control how deeply a task is worked through. Available now on web, coming to mobile and desktop.
User @cameronstow shared his daily three-tier setup: Light (GLM 5.3) for quick everyday tasks, High (Astra) for messaging, copywriting and heavy one-off work thanks to strong instruction-following and skills, and Ultra (Fable 5.1) for deep planning and long-running tasks where the orchestrator must chain decisions autonomously. He reports more consistent results since switching tiers more often.
Related event: Perplexity Computer Adds Effort Controls for Model Orchestration(4 posts)→
More from coding & agent
- One stale date silently broke a WhatsApp reply agent: 19 messages unanswered — petrusenko_max · 2026-11-02
- The 10X engineer is now just a SKILLS.md: 6 workflow rules for AI coding agents — mdancho84 · 2026-11-02
- Auditing my MCP credential broker: the worst hole was the config file — Relevant_Mousse_9117 · 2026-11-02
- AWS's open-source Strands Harness claims 45% cheaper than Claude Code, reigniting harness debate — blaizedsouza · 2026-11-02
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02
- Sketchy v0.1.6: AI diagrams use 29% fewer output tokens than plain text — Nkgsporty · 2026-11-02